Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    response

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ActionBar
    -0.08
    睛
    -0.07
    Optional
    -0.07
    MessageBox
    -0.07
     heavens
    -0.07
     blanket
    -0.07
     InputDecoration
    -0.07
    ابة
    -0.06
    ulu
    -0.06
    추
    -0.06
    POSITIVE LOGITS
    布尔
    0.07
    odic
    0.06
    ائع
    0.06
    Music
    0.06
     Serg
    0.06
     multicast
    0.06
    .bz
    0.06
    .tokens
    0.06
    VERAGE
    0.06
    ='../
    0.06
    Act Density 0.008%

    No Known Activations